Ripplewatch

Log what a customer said

log_customer_feedback

Record one piece of customer feedback in the customer's own words: a feature request, complaint or comment about the user's own product, with an optional 0-10 NPS score, who said it, and where it came from. Detractor and promoter reasons feed the same theme detection as win/loss, so they surface in get_trends. For a won or lost deal use log_win_loss; for a competitor coming up on a sales call use log_call_mentions; for a company fact or roadmap item use add_context_note. One piece of feedback per call. It adds a record and overwrites nothing. Only log what the user actually told you.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "summary": "<summary>"
    },
    "name": "log_customer_feedback"
  }
}

Input Schema

Name	Required	Description
`score`	No	NPS score 0-10, if this came from a survey.
`source`	No	Where it came from, e.g. 'support ticket', 'sales call', 'survey'.
`summary`	Yes	What the customer said.
`respondent`	No	Who said it (name or company), if known.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.6/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description explains that the tool adds a record and overwrites nothing, and that detractor/promoter reasons flow into the same theme detection surfaced by get_trends — useful downstream context an agent cannot infer from structured fields. It stops short of describing what comes back from a successful call, which matters slightly given there is no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, zero filler, and the most decision-relevant content is front-loaded: what it records first, then destination, then sibling routing, then per-call and overwrite constraints. The routing sentences are compact parallel constructions that are easy to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-parameter, single-object tool with no output schema, the definition covers purpose, exclusions, cardinality, and downstream effects thoroughly. The only missing piece is what a call returns, such as an identifier or confirmation, which would be helpful but is minor here.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, so the baseline is 3, but the description adds real meaning: the summary should be the customer's own words rather than a paraphrase, and the score is optional and tied to having NPS data. Those are content constraints the schema's "What the customer said" and "NPS score 0-10" do not fully convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Record one piece of customer feedback") plus the scope limits: the customer's own words, about the user's own product, with an optional 0-10 NPS score, respondent, and source. It then names each sibling that handles adjacent cases (log_win_loss, log_call_mentions, add_context_note), so an agent can separate this tool from the others without reading a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit routing rules are given for three alternatives with the exact condition that selects each (won/lost deal, competitor mentioned on a sales call, company fact or roadmap item). It also states a hard usage constraint, "One piece of feedback per call," and "Only log what the user actually told you," which heads off invented entries.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Ripplewatch tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?